Semantic transform: Weakly supervised semantic inference for relating visual attributes

Relative (comparative) attributes are promising for thematic ranking of visual entities, which also aids in recognition tasks. However, attribute rank learning often requires a substantial amount of relational supervision, which is highly tedious, and apparently impractical for real-world applications. In this paper, we introduce the Semantic Transform, which under minimal supervision, adaptively finds a semantic feature space along with a class ordering that is related in the best possible way. Such a semantic space is found for every attribute category. To relate the classes under weak supervision, the class ordering needs to be refined according to a cost function in an iterative procedure. This problem is ideally NP-hard, and we thus propose a constrained search tree formulation for the same. Driven by the adaptive semantic feature space representation, our model achieves the best results to date for all of the tasks of relative, absolute and zero-shot classification on two popular datasets. © 2013 IEEE.

Ecodesign innovation: Is 'early' always 'best'?

This paper explores ecodesign within the product development process (PDP), particularly focusing on the design stages. Previous research has highlighted the early stages as the 'best' place to integrate environmental issues. Here the early stage hypothesis is explored from the perspective of the industrial design department - the early stage designers. Being located at the earliest possible design stages of product development would mean that, were the hypothesis to hold true, industrial design would be the 'best' place to locate ecodesign. Empirical research was conducted with the Industrial Design Centre (IDC) of a global Electrical and Electronic goods manufacture. It used a qualitative, inductive research methodology, based on two 'live' design concept projects, participant observation within the department, and on several semi-structured interviews. Throughout this paper, the empirical work is compared and contrasted to ecodesign literature, specifically to models of ecodesign innovation and the product development process. Beginning by exploring of the early stage hypothesis, the paper concludes with a conceptual model of early stage ecodesign for the context in question.

N-best error simulation for training spoken dialogue systems

A recent trend in spoken dialogue research is the use of reinforcement learning to train dialogue systems in a simulated environment. Past researchers have shown that the types of errors that are simulated can have a significant effect on simulated dialogue performance. Since modern systems typically receive an N-best list of possible user utterances, it is important to be able to simulate a full N-best list of hypotheses. This paper presents a new method for simulating such errors based on logistic regression, as well as a new method for simulating the structure of N-best lists of semantics and their probabilities, based on the Dirichlet distribution. Off-line evaluations show that the new Dirichlet model results in a much closer match to the receiver operating characteristics (ROC) of the live data. Experiments also show that the logistic model gives confusions that are closer to the type of confusions observed in live situations. The hope is that these new error models will be able to improve the resulting performance of trained dialogue systems. © 2012 IEEE.